Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or movements involving items and their placement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.06
    4:0.06
    5:0.03
    6:0.08
    7:0.35
    8:0.02
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
     proverb
    -1.47
     Eisen
    -1.45
     tooltip
    -1.42
     Bash
    -1.39
     Ruler
    -1.39
    ipedia
    -1.38
     Physics
    -1.37
    Db
    -1.36
     Guinness
    -1.36
    Phys
    -1.33
    POSITIVE LOGITS
     goods
    1.85
     groceries
    1.84
     parcels
    1.79
     belongings
    1.78
     shipments
    1.75
     cargo
    1.73
     suitcase
    1.69
    emouth
    1.69
    igrants
    1.66
    okemon
    1.64
    Act Density 0.002%

    No Known Activations